Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2875 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.7371. Min Act: -0.0000

Data Index: 602903 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.6670. Min Act: -0.0000

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.5629. Min Act: -0.0000

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.3515. Min Act: -0.0000

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.5638. Min Act: -0.0000

Data Index: 734491 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1253758 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1541951 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.2819. Min Act: -0.0000

Data Index: 668068 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.3686. Min Act: -0.0000

Data Index: 529327 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.1313. Min Act: -0.0000

Data Index: 141529 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.1276. Min Act: -0.0000

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.3576. Min Act: -0.0000

Data Index: 1014762 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.0635. Min Act: -0.0000

Data Index: 1529318 (Python Code)

Max Activating Token Index: 787

Text #13

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.1799. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.0580. Min Act: -0.0000

Data Index: 1001923 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.1496. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.1506. Min Act: -0.0000

Data Index: 38070 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.3826. Min Act: -0.0000

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 2.7371. Min Range: -2.7371

Max Act: 2.1199. Min Act: -0.0000

Data Index: 412397 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 2.7371. Min Range: -2.7371

Max Act: 1.9854. Min Act: -0.0000

Data Index: 1211891 (C4 (Web Text))

Max Activating Token Index: 953